DeepTracer is a deep learning method for fast cryo-EM structure modeling of protein complexes, showing improved accuracy and efficiency compared to existing methods.

Proceedings of the National Academy of Sciences · Dec 23, 2020Peer-reviewedBioinformatics

Cascaded-CNN: Deep Learning to Predict Protein Backbone Structure from High-Resolution Cryo-EM Density Maps

Dong Si, Spencer A. Moritz, Jonas Pfab, Jie Hou, Renzhi Cao, Liguo Wang, Tianqi Wu, Jianlin Jack Cheng

Cascaded CNNs segmenting secondary structure, backbone and Cα voxels, plus tabu-search tracing, place 88.5% of Cα atoms within 3Å across 50 cryo-EM maps versus Phenix's 66.8%.

Scientific Reports · Mar 9, 2020Peer-reviewedMolecular Biology✦ In-depth digest

DeepTracer: Predicting Backbone Atomic Structure from High Resolution Cryo-EM Density Maps of Protein Complexes

Jonas Pfab, Dong Si

DeepTracer predicts protein backbone atoms, secondary structures, and amino acid types from cryo-EM density maps with high accuracy and speed.

bioRxiv · Feb 12, 2020 · PreprintBioinformatics

Automated Threshold Selection for Cryo-EM Density Maps

Jonas Pfab, Dong Si

This paper introduces an automated method for selecting density thresholds in cryo-EM maps to improve backbone structure prediction accuracy.

ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · Sep 4, 2019Peer-reviewedBioinformatics